Publish MR-IQA-2 E5 release
Browse files- .gitattributes +7 -0
- CHECKPOINTS.md +37 -0
- README.md +110 -1
- SHA256SUMS +7 -0
- SHA256SUMS.full +31 -0
- actors/README.md +4 -0
- actors/actor-completion-e5-step1455/chat_template.jinja +154 -0
- actors/actor-completion-e5-step1455/config.json +113 -0
- actors/actor-completion-e5-step1455/generation_config.json +9 -0
- actors/actor-completion-e5-step1455/model-00001-of-00002.safetensors +3 -0
- actors/actor-completion-e5-step1455/model-00002-of-00002.safetensors +3 -0
- actors/actor-completion-e5-step1455/model.safetensors.index.json +731 -0
- actors/actor-completion-e5-step1455/preprocessor_config.json +21 -0
- actors/actor-completion-e5-step1455/processor_config.json +60 -0
- actors/actor-completion-e5-step1455/provenance.json +92 -0
- actors/actor-completion-e5-step1455/tokenizer.json +3 -0
- actors/actor-completion-e5-step1455/tokenizer_config.json +33 -0
- chat_template.jinja +154 -0
- checkpoint_manifest.json +132 -0
- config.json +113 -0
- default_checkpoint_provenance.json +140 -0
- export_report.json +112 -0
- generation_config.json +9 -0
- judge/README.md +4 -0
- judge/source-e5/chat_template.jinja +154 -0
- judge/source-e5/config.json +113 -0
- judge/source-e5/generation_config.json +9 -0
- judge/source-e5/model-00001-of-00002.safetensors +3 -0
- judge/source-e5/model-00002-of-00002.safetensors +3 -0
- judge/source-e5/model.safetensors.index.json +731 -0
- judge/source-e5/preprocessor_config.json +21 -0
- judge/source-e5/processor_config.json +60 -0
- judge/source-e5/provenance.json +88 -0
- judge/source-e5/tokenizer.json +3 -0
- judge/source-e5/tokenizer_config.json +33 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model-index.json +74 -0
- model.safetensors.index.json +731 -0
- preprocessor_config.json +21 -0
- processor_config.json +60 -0
- provenance.template.json +29 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
- training_assets/README.md +4 -0
- training_assets/original_score_cache.manifest.json +42 -0
- training_assets/original_score_cache.sqlite +3 -0
.gitattributes
CHANGED
|
@@ -23,6 +23,7 @@
|
|
| 23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
*.tar filter=lfs diff=lfs merge=lfs -text
|
|
@@ -33,3 +34,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.sqlite filter=lfs diff=lfs merge=lfs -text
|
| 27 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 29 |
*.tar filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 34 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 36 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.json text eol=lf
|
| 38 |
+
*.md text eol=lf
|
| 39 |
+
*.jinja text eol=lf
|
| 40 |
+
actors/actor-completion-e5-step1455/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
judge/source-e5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
CHECKPOINTS.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Released checkpoints
|
| 2 |
+
|
| 3 |
+
`from_pretrained("RobinY99/MR-IQA-2")` loads the field-credit Actor. Use
|
| 4 |
+
`subfolder=` for the other two E5 models.
|
| 5 |
+
|
| 6 |
+
| Asset | Step | Hub location |
|
| 7 |
+
|---|---:|---|
|
| 8 |
+
| `actor-field-e5-step1455` | 1,455 | repository root |
|
| 9 |
+
| `source-e5-judge-step725` | 725 | `judge/source-e5` |
|
| 10 |
+
| `actor-completion-e5-step1455` | 1,455 | `actors/actor-completion-e5-step1455` |
|
| 11 |
+
|
| 12 |
+
Each model directory contains Transformers configuration, processor,
|
| 13 |
+
tokenizer, chat template, and safetensors weight shards.
|
| 14 |
+
|
| 15 |
+
## Training cache
|
| 16 |
+
|
| 17 |
+
`training_assets/original_score_cache.sqlite` contains 10,073 source-image
|
| 18 |
+
scores from `source-e5-judge-step725`. Its schema is
|
| 19 |
+
`vf_original_score_cache_e5_judge_e5prompt_portable_v1`.
|
| 20 |
+
|
| 21 |
+
## Download
|
| 22 |
+
|
| 23 |
+
```python
|
| 24 |
+
from huggingface_hub import snapshot_download
|
| 25 |
+
|
| 26 |
+
field_actor = snapshot_download(
|
| 27 |
+
"RobinY99/MR-IQA-2",
|
| 28 |
+
revision="<hub-commit>",
|
| 29 |
+
allow_patterns=["*.json", "*.jinja", "*.safetensors"],
|
| 30 |
+
)
|
| 31 |
+
|
| 32 |
+
judge = snapshot_download(
|
| 33 |
+
"RobinY99/MR-IQA-2",
|
| 34 |
+
revision="<hub-commit>",
|
| 35 |
+
allow_patterns=["judge/source-e5/**"],
|
| 36 |
+
)
|
| 37 |
+
```
|
README.md
CHANGED
|
@@ -1,3 +1,112 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: image-text-to-text
|
| 7 |
+
base_model: Qwen/Qwen3.5-4B
|
| 8 |
+
tags:
|
| 9 |
+
- image-quality-assessment
|
| 10 |
+
- vision-language
|
| 11 |
+
- reinforcement-learning
|
| 12 |
+
- grpo
|
| 13 |
+
- image-editing
|
| 14 |
+
- research
|
| 15 |
---
|
| 16 |
+
|
| 17 |
+
# MR-IQA-2
|
| 18 |
+
|
| 19 |
+
MR-IQA-2 trains a multimodal Actor to assess image quality and propose an
|
| 20 |
+
image-editing instruction. A frozen Editor and IQA Judge provide the reasoning
|
| 21 |
+
reward during training.
|
| 22 |
+
|
| 23 |
+
## Models
|
| 24 |
+
|
| 25 |
+
| Model | Hub location | Use |
|
| 26 |
+
|---|---|---|
|
| 27 |
+
| `actor-field-e5-step1455` | repository root | Default Actor |
|
| 28 |
+
| `source-e5-judge-step725` | `judge/source-e5` | Frozen IQA Judge |
|
| 29 |
+
| `actor-completion-e5-step1455` | `actors/actor-completion-e5-step1455` | Completion-wide ablation |
|
| 30 |
+
|
| 31 |
+
The default Actor uses field-specific credit and component KL. The
|
| 32 |
+
completion-wide ablation has a 1.000 top-template rate in its `solution`
|
| 33 |
+
field. See [CHECKPOINTS.md](CHECKPOINTS.md) for paths.
|
| 34 |
+
|
| 35 |
+
## Usage
|
| 36 |
+
|
| 37 |
+
Pin a Hub commit for reproducible loading:
|
| 38 |
+
|
| 39 |
+
```python
|
| 40 |
+
from transformers import AutoModelForImageTextToText, AutoProcessor
|
| 41 |
+
|
| 42 |
+
repo_id = "RobinY99/MR-IQA-2"
|
| 43 |
+
revision = "<hub-commit>"
|
| 44 |
+
|
| 45 |
+
processor = AutoProcessor.from_pretrained(
|
| 46 |
+
repo_id,
|
| 47 |
+
revision=revision,
|
| 48 |
+
trust_remote_code=True,
|
| 49 |
+
)
|
| 50 |
+
model = AutoModelForImageTextToText.from_pretrained(
|
| 51 |
+
repo_id,
|
| 52 |
+
revision=revision,
|
| 53 |
+
torch_dtype="auto",
|
| 54 |
+
device_map="auto",
|
| 55 |
+
use_safetensors=True,
|
| 56 |
+
trust_remote_code=True,
|
| 57 |
+
)
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
Load the Judge by adding `subfolder="judge/source-e5"` to both calls. Load the
|
| 61 |
+
completion-wide Actor with
|
| 62 |
+
`subfolder="actors/actor-completion-e5-step1455"`. Review repository code
|
| 63 |
+
before enabling `trust_remote_code`.
|
| 64 |
+
|
| 65 |
+
The prompt, parser, training, and evaluation commands are in the
|
| 66 |
+
[GitHub repository](https://github.com/RobinY99/MR-IQA-2).
|
| 67 |
+
|
| 68 |
+
## Output
|
| 69 |
+
|
| 70 |
+
The Actor returns:
|
| 71 |
+
|
| 72 |
+
- `evidence`: image-grounded quality observations;
|
| 73 |
+
- `solution`: an image-editing instruction;
|
| 74 |
+
- `rating`: the predicted quality score.
|
| 75 |
+
|
| 76 |
+
## Results
|
| 77 |
+
|
| 78 |
+
### Validation (200 rows)
|
| 79 |
+
|
| 80 |
+
| Checkpoint | Step | PLCC | SRCC | MAE | Mean reasoning reward | Top solution rate |
|
| 81 |
+
|---|---:|---:|---:|---:|---:|---:|
|
| 82 |
+
| Field-credit E5 | 1455 | 0.935394 | 0.919533 | 0.354589 | 0.292849 | 0.010 |
|
| 83 |
+
| Completion-wide E5 | 1455 | 0.928980 | 0.915821 | 0.997127 | 0.462215 | 1.000 |
|
| 84 |
+
| Source Judge E5 | 725 | 0.947970 | 0.934169 | 0.439320 | — | — |
|
| 85 |
+
|
| 86 |
+
### Field-credit E5 generalization
|
| 87 |
+
|
| 88 |
+
| Dataset | Rows | PLCC | SRCC | MAE | Format success |
|
| 89 |
+
|---|---:|---:|---:|---:|---:|
|
| 90 |
+
| AGIQA-3K | 2,982 | 0.808912 | 0.739095 | 0.601462 | 0.989604 |
|
| 91 |
+
| CSIQ | 866 | 0.824399 | 0.785005 | 0.587842 | 0.998845 |
|
| 92 |
+
| KADID-10K | 10,125 | 0.667023 | 0.668921 | 0.975945 | 0.982815 |
|
| 93 |
+
| KonIQ-10K | 2,010 | 0.936707 | 0.917184 | 0.353084 | 0.997015 |
|
| 94 |
+
| LIVE-Wild | 1,162 | 0.893301 | 0.863127 | 0.373541 | 1.000000 |
|
| 95 |
+
| SPAQ | 11,125 | 0.899730 | 0.899407 | 0.366480 | 0.998742 |
|
| 96 |
+
| Macro | 28,270 | 0.838345 | 0.812123 | 0.543059 | — |
|
| 97 |
+
|
| 98 |
+
These are Actor rating metrics.
|
| 99 |
+
|
| 100 |
+
## Training
|
| 101 |
+
|
| 102 |
+
The field-credit run uses sampled-k3 component KL with beta 0.02 for reasoning
|
| 103 |
+
and rating. ViT and aligner parameters are frozen. Training uses five epochs,
|
| 104 |
+
291 optimizer updates per epoch, a 160-token completion cap, and a
|
| 105 |
+
soft-overlong penalty beginning at token 144.
|
| 106 |
+
|
| 107 |
+
## License
|
| 108 |
+
|
| 109 |
+
The Actor and Judge are derivatives of [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)
|
| 110 |
+
and are released under Apache-2.0. Companion code is MIT licensed. Editor
|
| 111 |
+
weights and datasets are not included and remain subject to their upstream
|
| 112 |
+
licenses.
|
SHA256SUMS
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2d75ecd7028d83e74af8bbd0791c55f74062c1d4ac030f149dfc81de7681d382 model-00001-of-00002.safetensors
|
| 2 |
+
d492fb65ac0330c50d50d1bd233db966fc71a1236799c1472c55b3c4171cbca9 model-00002-of-00002.safetensors
|
| 3 |
+
c75ddabb26f9c00abfe462fc6038079c88576aa6fee406a669f76881e3bf2f1b judge/source-e5/model-00001-of-00002.safetensors
|
| 4 |
+
0b11a6610858678b3dfed3c06803818ae1d5bfcfe366374f515e08410283a2c9 judge/source-e5/model-00002-of-00002.safetensors
|
| 5 |
+
2d33b8df75b71df469b110d4cccf7d49be99f6a50d33a749cecb8f53453065c6 actors/actor-completion-e5-step1455/model-00001-of-00002.safetensors
|
| 6 |
+
1d4590bc4e7b99a11723e498940914e0ac2519924556b08813eac39dfd4a0378 actors/actor-completion-e5-step1455/model-00002-of-00002.safetensors
|
| 7 |
+
7d5410f57f17ff1957e7cbeef951ac01973c0bce97da6f700d61bb222bdd5532 training_assets/original_score_cache.sqlite
|
SHA256SUMS.full
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
044807d4c2f35cc7f9ffbbbe0bd9800256e27f5337069cd69e6c8eba0c98e604 actors/actor-completion-e5-step1455/model.safetensors.index.json
|
| 2 |
+
044807d4c2f35cc7f9ffbbbe0bd9800256e27f5337069cd69e6c8eba0c98e604 judge/source-e5/model.safetensors.index.json
|
| 3 |
+
044807d4c2f35cc7f9ffbbbe0bd9800256e27f5337069cd69e6c8eba0c98e604 model.safetensors.index.json
|
| 4 |
+
06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 actors/actor-completion-e5-step1455/tokenizer.json
|
| 5 |
+
06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 judge/source-e5/tokenizer.json
|
| 6 |
+
06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 tokenizer.json
|
| 7 |
+
0b11a6610858678b3dfed3c06803818ae1d5bfcfe366374f515e08410283a2c9 judge/source-e5/model-00002-of-00002.safetensors
|
| 8 |
+
1d4590bc4e7b99a11723e498940914e0ac2519924556b08813eac39dfd4a0378 actors/actor-completion-e5-step1455/model-00002-of-00002.safetensors
|
| 9 |
+
27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516 actors/actor-completion-e5-step1455/preprocessor_config.json
|
| 10 |
+
27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516 judge/source-e5/preprocessor_config.json
|
| 11 |
+
27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516 preprocessor_config.json
|
| 12 |
+
2d33b8df75b71df469b110d4cccf7d49be99f6a50d33a749cecb8f53453065c6 actors/actor-completion-e5-step1455/model-00001-of-00002.safetensors
|
| 13 |
+
2d75ecd7028d83e74af8bbd0791c55f74062c1d4ac030f149dfc81de7681d382 model-00001-of-00002.safetensors
|
| 14 |
+
792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b actors/actor-completion-e5-step1455/tokenizer_config.json
|
| 15 |
+
792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b judge/source-e5/tokenizer_config.json
|
| 16 |
+
792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b tokenizer_config.json
|
| 17 |
+
7d5410f57f17ff1957e7cbeef951ac01973c0bce97da6f700d61bb222bdd5532 training_assets/original_score_cache.sqlite
|
| 18 |
+
a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715 actors/actor-completion-e5-step1455/chat_template.jinja
|
| 19 |
+
a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715 chat_template.jinja
|
| 20 |
+
a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715 judge/source-e5/chat_template.jinja
|
| 21 |
+
c5635b1910c68e43527ed092d9f964cc0ae0e6b97f91cb0dda9878dba8e5de99 actors/actor-completion-e5-step1455/config.json
|
| 22 |
+
c5635b1910c68e43527ed092d9f964cc0ae0e6b97f91cb0dda9878dba8e5de99 config.json
|
| 23 |
+
c5635b1910c68e43527ed092d9f964cc0ae0e6b97f91cb0dda9878dba8e5de99 judge/source-e5/config.json
|
| 24 |
+
c75ddabb26f9c00abfe462fc6038079c88576aa6fee406a669f76881e3bf2f1b judge/source-e5/model-00001-of-00002.safetensors
|
| 25 |
+
d492fb65ac0330c50d50d1bd233db966fc71a1236799c1472c55b3c4171cbca9 model-00002-of-00002.safetensors
|
| 26 |
+
d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1 actors/actor-completion-e5-step1455/processor_config.json
|
| 27 |
+
d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1 judge/source-e5/processor_config.json
|
| 28 |
+
d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1 processor_config.json
|
| 29 |
+
f7c35afc4eda09ee1a9cbe029b030dc9875ab3c201401c48044448e8153acea2 actors/actor-completion-e5-step1455/generation_config.json
|
| 30 |
+
f7c35afc4eda09ee1a9cbe029b030dc9875ab3c201401c48044448e8153acea2 generation_config.json
|
| 31 |
+
f7c35afc4eda09ee1a9cbe029b030dc9875ab3c201401c48044448e8153acea2 judge/source-e5/generation_config.json
|
actors/README.md
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Actor checkpoint
|
| 2 |
+
|
| 3 |
+
`actor-completion-e5-step1455` is the completion-wide E5 ablation. The default
|
| 4 |
+
field-credit E5 Actor is stored at repository root.
|
actors/actor-completion-e5-step1455/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
actors/actor-completion-e5-step1455/config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 2560,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 9216,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": 248044,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": true,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": true,
|
| 91 |
+
"transformers_version": "5.12.1",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 24,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1024,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4096,
|
| 103 |
+
"model_type": "qwen3_5_vision",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 2560,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
actors/actor-completion-e5-step1455/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248044,
|
| 5 |
+
248046
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "5.12.1",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
actors/actor-completion-e5-step1455/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d33b8df75b71df469b110d4cccf7d49be99f6a50d33a749cecb8f53453065c6
|
| 3 |
+
size 4972947968
|
actors/actor-completion-e5-step1455/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d4590bc4e7b99a11723e498940914e0ac2519924556b08813eac39dfd4a0378
|
| 3 |
+
size 4105672464
|
actors/actor-completion-e5-step1455/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,731 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 504320,
|
| 4 |
+
"total_size": 9078531072
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 730 |
+
}
|
| 731 |
+
}
|
actors/actor-completion-e5-step1455/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
actors/actor-completion-e5-step1455/processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
actors/actor-completion-e5-step1455/provenance.json
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"asset_id": "actor-completion-e5-step1455",
|
| 3 |
+
"exported_at_utc": "2026-08-10T08:34:19.797359+00:00",
|
| 4 |
+
"exporter_version": "mriqa2_hf_export_v1",
|
| 5 |
+
"files": [
|
| 6 |
+
{
|
| 7 |
+
"name": "model-00001-of-00002.safetensors",
|
| 8 |
+
"sha256": "2d33b8df75b71df469b110d4cccf7d49be99f6a50d33a749cecb8f53453065c6",
|
| 9 |
+
"size_bytes": 4972947968
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"name": "model-00002-of-00002.safetensors",
|
| 13 |
+
"sha256": "1d4590bc4e7b99a11723e498940914e0ac2519924556b08813eac39dfd4a0378",
|
| 14 |
+
"size_bytes": 4105672464
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"name": "model.safetensors.index.json",
|
| 18 |
+
"sha256": "044807d4c2f35cc7f9ffbbbe0bd9800256e27f5337069cd69e6c8eba0c98e604",
|
| 19 |
+
"size_bytes": 66232
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"name": "config.json",
|
| 23 |
+
"sha256": "c5635b1910c68e43527ed092d9f964cc0ae0e6b97f91cb0dda9878dba8e5de99",
|
| 24 |
+
"size_bytes": 2929
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"name": "generation_config.json",
|
| 28 |
+
"sha256": "f7c35afc4eda09ee1a9cbe029b030dc9875ab3c201401c48044448e8153acea2",
|
| 29 |
+
"size_bytes": 138
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"name": "preprocessor_config.json",
|
| 33 |
+
"sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
|
| 34 |
+
"size_bytes": 390
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"name": "processor_config.json",
|
| 38 |
+
"sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
|
| 39 |
+
"size_bytes": 1191
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"name": "tokenizer.json",
|
| 43 |
+
"sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
|
| 44 |
+
"size_bytes": 19989325
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"name": "tokenizer_config.json",
|
| 48 |
+
"sha256": "792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b",
|
| 49 |
+
"size_bytes": 1165
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"name": "chat_template.jinja",
|
| 53 |
+
"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
|
| 54 |
+
"size_bytes": 7756
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"hub_subfolder": "actors/actor-completion-e5-step1455",
|
| 58 |
+
"schema_version": "mriqa2_checkpoint_provenance_v1",
|
| 59 |
+
"selection": {
|
| 60 |
+
"recommended": false,
|
| 61 |
+
"research_status": "ablation_only_known_solution_collapse",
|
| 62 |
+
"status": "ablation_final"
|
| 63 |
+
},
|
| 64 |
+
"source_identity": {
|
| 65 |
+
"file_count": 10,
|
| 66 |
+
"ignored_source_entries": [
|
| 67 |
+
{
|
| 68 |
+
"kind": "file",
|
| 69 |
+
"name": "provenance.json"
|
| 70 |
+
}
|
| 71 |
+
],
|
| 72 |
+
"selected_export_tree_sha256": "14d801bffb7f65217a899b10c0735d3d2e37436dd799c3b6352f085845e5b374",
|
| 73 |
+
"source_checkpoint_tree_sha256_recorded": "5a565e49c54c0d6fc52be57aece120c529b23541774f18b7b4d5fb404b082345",
|
| 74 |
+
"total_bytes": 9098689558
|
| 75 |
+
},
|
| 76 |
+
"source_logical_id": "actor-completion-e5-step1455",
|
| 77 |
+
"training": {
|
| 78 |
+
"base_model": "Qwen/Qwen3.5-4B",
|
| 79 |
+
"epoch": 5,
|
| 80 |
+
"global_step": 1455,
|
| 81 |
+
"mode": "completion_wide_credit_global_kl_0.02"
|
| 82 |
+
},
|
| 83 |
+
"validation": {
|
| 84 |
+
"house_family_rate": 1.0,
|
| 85 |
+
"mae": 0.9971267892365984,
|
| 86 |
+
"mean_reasoning_reward_zero_filled": 0.4622147632541047,
|
| 87 |
+
"plcc": 0.9289800766182985,
|
| 88 |
+
"rows": 200,
|
| 89 |
+
"srcc": 0.9158209053578285,
|
| 90 |
+
"top_normalized_solution_rate": 1.0
|
| 91 |
+
}
|
| 92 |
+
}
|
actors/actor-completion-e5-step1455/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
actors/actor-completion-e5-step1455/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
checkpoint_manifest.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "mriqa2_hf_checkpoint_manifest_v1",
|
| 3 |
+
"release_state": "ready_for_upload",
|
| 4 |
+
"repository_id": "RobinY99/MR-IQA-2",
|
| 5 |
+
"model_weights_license": "Apache-2.0",
|
| 6 |
+
"companion_code_license": "MIT",
|
| 7 |
+
"editor_weights_included": false,
|
| 8 |
+
"default_asset_id": "actor-field-e5-step1455",
|
| 9 |
+
"expected_asset_count": 3,
|
| 10 |
+
"expected_total_files": 30,
|
| 11 |
+
"expected_total_bytes": 27296068674,
|
| 12 |
+
"expected_release_payload_files": 31,
|
| 13 |
+
"expected_release_payload_bytes": 27311072322,
|
| 14 |
+
"required_files": [
|
| 15 |
+
"model-00001-of-00002.safetensors",
|
| 16 |
+
"model-00002-of-00002.safetensors",
|
| 17 |
+
"model.safetensors.index.json",
|
| 18 |
+
"config.json",
|
| 19 |
+
"generation_config.json",
|
| 20 |
+
"preprocessor_config.json",
|
| 21 |
+
"processor_config.json",
|
| 22 |
+
"tokenizer.json",
|
| 23 |
+
"tokenizer_config.json",
|
| 24 |
+
"chat_template.jinja"
|
| 25 |
+
],
|
| 26 |
+
"training_assets": [
|
| 27 |
+
{
|
| 28 |
+
"asset_id": "portable-original-score-cache-v1",
|
| 29 |
+
"hub_path": "training_assets/original_score_cache.sqlite",
|
| 30 |
+
"release_state": "ready",
|
| 31 |
+
"schema_version": "vf_original_score_cache_e5_judge_e5prompt_portable_v1",
|
| 32 |
+
"actor_id": "source-e5-judge-step725-original-score",
|
| 33 |
+
"judge_id": "source-e5-judge-step725",
|
| 34 |
+
"logical_model_uri": "hf://RobinY99/MR-IQA-2/judge/source-e5",
|
| 35 |
+
"manifest_path": "training_assets/original_score_cache.manifest.json",
|
| 36 |
+
"bytes": 15003648,
|
| 37 |
+
"row_count": 10073,
|
| 38 |
+
"sample_count": 10073,
|
| 39 |
+
"sha256": "7d5410f57f17ff1957e7cbeef951ac01973c0bce97da6f700d61bb222bdd5532",
|
| 40 |
+
"rating": {
|
| 41 |
+
"min": 0.83,
|
| 42 |
+
"max": 4.23,
|
| 43 |
+
"mean": 3.1357688871239398
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"assets": [
|
| 48 |
+
{
|
| 49 |
+
"asset_id": "actor-field-e5-step1455",
|
| 50 |
+
"source_logical_id": "actor-field-e5-step1455",
|
| 51 |
+
"role": "actor",
|
| 52 |
+
"hub_subfolder": ".",
|
| 53 |
+
"training_mode": "field_credit_component_kl_0.02",
|
| 54 |
+
"epoch": 5,
|
| 55 |
+
"global_step": 1455,
|
| 56 |
+
"selection": "pipeline_best",
|
| 57 |
+
"recommended": true,
|
| 58 |
+
"research_status": "release_default",
|
| 59 |
+
"source_checkpoint_tree_sha256": "65935012bcaef8c027fb9d233e563c5fea3515e2011e1dd046209b222afe9e94",
|
| 60 |
+
"expected_export_tree_sha256": "3e372f548631e3ebbb23e9d8493cb2d50aa482b1941025deda907b35e0a97edb",
|
| 61 |
+
"expected_file_count": 10,
|
| 62 |
+
"expected_total_bytes": 9098689558,
|
| 63 |
+
"verified_weight_sha256": {
|
| 64 |
+
"model-00001-of-00002.safetensors": "2d75ecd7028d83e74af8bbd0791c55f74062c1d4ac030f149dfc81de7681d382",
|
| 65 |
+
"model-00002-of-00002.safetensors": "d492fb65ac0330c50d50d1bd233db966fc71a1236799c1472c55b3c4171cbca9"
|
| 66 |
+
},
|
| 67 |
+
"validation": {
|
| 68 |
+
"rows": 200,
|
| 69 |
+
"plcc": 0.9353936795729616,
|
| 70 |
+
"srcc": 0.919533309066156,
|
| 71 |
+
"mae": 0.3545886555344741,
|
| 72 |
+
"mean_reasoning_reward_zero_filled": 0.2928487210092652,
|
| 73 |
+
"house_family_rate": 0.0,
|
| 74 |
+
"top_normalized_solution_rate": 0.01
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"asset_id": "source-e5-judge-step725",
|
| 79 |
+
"source_logical_id": "source-e5-judge-step725",
|
| 80 |
+
"role": "judge",
|
| 81 |
+
"hub_subfolder": "judge/source-e5",
|
| 82 |
+
"training_mode": "source_e5_judge",
|
| 83 |
+
"epoch": 5,
|
| 84 |
+
"global_step": 725,
|
| 85 |
+
"selection": "frozen_source_judge",
|
| 86 |
+
"recommended": true,
|
| 87 |
+
"research_status": "required_for_released_judge_protocol",
|
| 88 |
+
"source_checkpoint_tree_sha256": "e25415173aacf515e97d5d561c6647a7a84f586061f3a9b2ab3fc079fe21be0a",
|
| 89 |
+
"expected_export_tree_sha256": "21b232a1a30dc765f3e7cf16c00fd270e4be354615fea0120e32f975e2777e5c",
|
| 90 |
+
"expected_file_count": 10,
|
| 91 |
+
"expected_total_bytes": 9098689558,
|
| 92 |
+
"verified_weight_sha256": {
|
| 93 |
+
"model-00001-of-00002.safetensors": "c75ddabb26f9c00abfe462fc6038079c88576aa6fee406a669f76881e3bf2f1b",
|
| 94 |
+
"model-00002-of-00002.safetensors": "0b11a6610858678b3dfed3c06803818ae1d5bfcfe366374f515e08410283a2c9"
|
| 95 |
+
},
|
| 96 |
+
"validation": {
|
| 97 |
+
"plcc": 0.94797,
|
| 98 |
+
"srcc": 0.934169,
|
| 99 |
+
"mae": 0.43932
|
| 100 |
+
}
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"asset_id": "actor-completion-e5-step1455",
|
| 104 |
+
"source_logical_id": "actor-completion-e5-step1455",
|
| 105 |
+
"role": "actor",
|
| 106 |
+
"hub_subfolder": "actors/actor-completion-e5-step1455",
|
| 107 |
+
"training_mode": "completion_wide_credit_global_kl_0.02",
|
| 108 |
+
"epoch": 5,
|
| 109 |
+
"global_step": 1455,
|
| 110 |
+
"selection": "ablation_final",
|
| 111 |
+
"recommended": false,
|
| 112 |
+
"research_status": "ablation_only_known_solution_collapse",
|
| 113 |
+
"source_checkpoint_tree_sha256": "5a565e49c54c0d6fc52be57aece120c529b23541774f18b7b4d5fb404b082345",
|
| 114 |
+
"expected_export_tree_sha256": "14d801bffb7f65217a899b10c0735d3d2e37436dd799c3b6352f085845e5b374",
|
| 115 |
+
"expected_file_count": 10,
|
| 116 |
+
"expected_total_bytes": 9098689558,
|
| 117 |
+
"verified_weight_sha256": {
|
| 118 |
+
"model-00001-of-00002.safetensors": "2d33b8df75b71df469b110d4cccf7d49be99f6a50d33a749cecb8f53453065c6",
|
| 119 |
+
"model-00002-of-00002.safetensors": "1d4590bc4e7b99a11723e498940914e0ac2519924556b08813eac39dfd4a0378"
|
| 120 |
+
},
|
| 121 |
+
"validation": {
|
| 122 |
+
"rows": 200,
|
| 123 |
+
"plcc": 0.9289800766182985,
|
| 124 |
+
"srcc": 0.9158209053578285,
|
| 125 |
+
"mae": 0.9971267892365984,
|
| 126 |
+
"mean_reasoning_reward_zero_filled": 0.4622147632541047,
|
| 127 |
+
"house_family_rate": 1.0,
|
| 128 |
+
"top_normalized_solution_rate": 1.0
|
| 129 |
+
}
|
| 130 |
+
}
|
| 131 |
+
]
|
| 132 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 2560,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 9216,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": 248044,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": true,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": true,
|
| 91 |
+
"transformers_version": "5.12.1",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 24,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1024,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4096,
|
| 103 |
+
"model_type": "qwen3_5_vision",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 2560,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
default_checkpoint_provenance.json
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"asset_id": "actor-field-e5-step1455",
|
| 3 |
+
"exported_at_utc": "2026-08-10T08:34:19.797359+00:00",
|
| 4 |
+
"exporter_version": "mriqa2_hf_export_v1",
|
| 5 |
+
"files": [
|
| 6 |
+
{
|
| 7 |
+
"name": "model-00001-of-00002.safetensors",
|
| 8 |
+
"sha256": "2d75ecd7028d83e74af8bbd0791c55f74062c1d4ac030f149dfc81de7681d382",
|
| 9 |
+
"size_bytes": 4972947968
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"name": "model-00002-of-00002.safetensors",
|
| 13 |
+
"sha256": "d492fb65ac0330c50d50d1bd233db966fc71a1236799c1472c55b3c4171cbca9",
|
| 14 |
+
"size_bytes": 4105672464
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"name": "model.safetensors.index.json",
|
| 18 |
+
"sha256": "044807d4c2f35cc7f9ffbbbe0bd9800256e27f5337069cd69e6c8eba0c98e604",
|
| 19 |
+
"size_bytes": 66232
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"name": "config.json",
|
| 23 |
+
"sha256": "c5635b1910c68e43527ed092d9f964cc0ae0e6b97f91cb0dda9878dba8e5de99",
|
| 24 |
+
"size_bytes": 2929
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"name": "generation_config.json",
|
| 28 |
+
"sha256": "f7c35afc4eda09ee1a9cbe029b030dc9875ab3c201401c48044448e8153acea2",
|
| 29 |
+
"size_bytes": 138
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"name": "preprocessor_config.json",
|
| 33 |
+
"sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
|
| 34 |
+
"size_bytes": 390
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"name": "processor_config.json",
|
| 38 |
+
"sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
|
| 39 |
+
"size_bytes": 1191
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"name": "tokenizer.json",
|
| 43 |
+
"sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
|
| 44 |
+
"size_bytes": 19989325
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"name": "tokenizer_config.json",
|
| 48 |
+
"sha256": "792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b",
|
| 49 |
+
"size_bytes": 1165
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"name": "chat_template.jinja",
|
| 53 |
+
"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
|
| 54 |
+
"size_bytes": 7756
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"hub_subfolder": ".",
|
| 58 |
+
"schema_version": "mriqa2_checkpoint_provenance_v1",
|
| 59 |
+
"selection": {
|
| 60 |
+
"recommended": true,
|
| 61 |
+
"research_status": "release_default",
|
| 62 |
+
"status": "pipeline_best"
|
| 63 |
+
},
|
| 64 |
+
"source_identity": {
|
| 65 |
+
"file_count": 10,
|
| 66 |
+
"ignored_source_entries": [
|
| 67 |
+
{
|
| 68 |
+
"kind": "file",
|
| 69 |
+
"name": ".gitattributes"
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"kind": "file",
|
| 73 |
+
"name": "CHECKPOINTS.md"
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"kind": "file",
|
| 77 |
+
"name": "README.md"
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"kind": "file",
|
| 81 |
+
"name": "SHA256SUMS"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"kind": "file",
|
| 85 |
+
"name": "SHA256SUMS.full"
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"kind": "directory",
|
| 89 |
+
"name": "actors"
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"kind": "file",
|
| 93 |
+
"name": "checkpoint_manifest.json"
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"kind": "file",
|
| 97 |
+
"name": "default_checkpoint_provenance.json"
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"kind": "file",
|
| 101 |
+
"name": "export_report.json"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"kind": "directory",
|
| 105 |
+
"name": "judge"
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"kind": "file",
|
| 109 |
+
"name": "model-index.json"
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"kind": "file",
|
| 113 |
+
"name": "provenance.template.json"
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"kind": "directory",
|
| 117 |
+
"name": "training_assets"
|
| 118 |
+
}
|
| 119 |
+
],
|
| 120 |
+
"selected_export_tree_sha256": "3e372f548631e3ebbb23e9d8493cb2d50aa482b1941025deda907b35e0a97edb",
|
| 121 |
+
"source_checkpoint_tree_sha256_recorded": "65935012bcaef8c027fb9d233e563c5fea3515e2011e1dd046209b222afe9e94",
|
| 122 |
+
"total_bytes": 9098689558
|
| 123 |
+
},
|
| 124 |
+
"source_logical_id": "actor-field-e5-step1455",
|
| 125 |
+
"training": {
|
| 126 |
+
"base_model": "Qwen/Qwen3.5-4B",
|
| 127 |
+
"epoch": 5,
|
| 128 |
+
"global_step": 1455,
|
| 129 |
+
"mode": "field_credit_component_kl_0.02"
|
| 130 |
+
},
|
| 131 |
+
"validation": {
|
| 132 |
+
"house_family_rate": 0.0,
|
| 133 |
+
"mae": 0.3545886555344741,
|
| 134 |
+
"mean_reasoning_reward_zero_filled": 0.2928487210092652,
|
| 135 |
+
"plcc": 0.9353936795729616,
|
| 136 |
+
"rows": 200,
|
| 137 |
+
"srcc": 0.919533309066156,
|
| 138 |
+
"top_normalized_solution_rate": 0.01
|
| 139 |
+
}
|
| 140 |
+
}
|
export_report.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"asset_count": 3,
|
| 3 |
+
"assets": [
|
| 4 |
+
{
|
| 5 |
+
"asset_id": "actor-field-e5-step1455",
|
| 6 |
+
"export_tree_sha256": "3e372f548631e3ebbb23e9d8493cb2d50aa482b1941025deda907b35e0a97edb",
|
| 7 |
+
"file_count": 10,
|
| 8 |
+
"ignored_source_entries": [
|
| 9 |
+
{
|
| 10 |
+
"kind": "file",
|
| 11 |
+
"name": ".gitattributes"
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"kind": "file",
|
| 15 |
+
"name": "CHECKPOINTS.md"
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"kind": "file",
|
| 19 |
+
"name": "README.md"
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"kind": "file",
|
| 23 |
+
"name": "SHA256SUMS"
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"kind": "file",
|
| 27 |
+
"name": "SHA256SUMS.full"
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"kind": "directory",
|
| 31 |
+
"name": "actors"
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"kind": "file",
|
| 35 |
+
"name": "checkpoint_manifest.json"
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"kind": "file",
|
| 39 |
+
"name": "default_checkpoint_provenance.json"
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"kind": "file",
|
| 43 |
+
"name": "export_report.json"
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"kind": "directory",
|
| 47 |
+
"name": "judge"
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"kind": "file",
|
| 51 |
+
"name": "model-index.json"
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"kind": "file",
|
| 55 |
+
"name": "provenance.template.json"
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"kind": "directory",
|
| 59 |
+
"name": "training_assets"
|
| 60 |
+
}
|
| 61 |
+
],
|
| 62 |
+
"source_checkpoint_tree_sha256_recorded": "65935012bcaef8c027fb9d233e563c5fea3515e2011e1dd046209b222afe9e94",
|
| 63 |
+
"total_bytes": 9098689558
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"asset_id": "source-e5-judge-step725",
|
| 67 |
+
"export_tree_sha256": "21b232a1a30dc765f3e7cf16c00fd270e4be354615fea0120e32f975e2777e5c",
|
| 68 |
+
"file_count": 10,
|
| 69 |
+
"ignored_source_entries": [
|
| 70 |
+
{
|
| 71 |
+
"kind": "file",
|
| 72 |
+
"name": "provenance.json"
|
| 73 |
+
}
|
| 74 |
+
],
|
| 75 |
+
"source_checkpoint_tree_sha256_recorded": "e25415173aacf515e97d5d561c6647a7a84f586061f3a9b2ab3fc079fe21be0a",
|
| 76 |
+
"total_bytes": 9098689558
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"asset_id": "actor-completion-e5-step1455",
|
| 80 |
+
"export_tree_sha256": "14d801bffb7f65217a899b10c0735d3d2e37436dd799c3b6352f085845e5b374",
|
| 81 |
+
"file_count": 10,
|
| 82 |
+
"ignored_source_entries": [
|
| 83 |
+
{
|
| 84 |
+
"kind": "file",
|
| 85 |
+
"name": "provenance.json"
|
| 86 |
+
}
|
| 87 |
+
],
|
| 88 |
+
"source_checkpoint_tree_sha256_recorded": "5a565e49c54c0d6fc52be57aece120c529b23541774f18b7b4d5fb404b082345",
|
| 89 |
+
"total_bytes": 9098689558
|
| 90 |
+
}
|
| 91 |
+
],
|
| 92 |
+
"exported_at_utc": "2026-08-10T08:34:19.797359+00:00",
|
| 93 |
+
"exporter_version": "mriqa2_hf_export_v1",
|
| 94 |
+
"model_file_count": 30,
|
| 95 |
+
"model_total_bytes": 27296068674,
|
| 96 |
+
"ready_for_upload": true,
|
| 97 |
+
"release_payload_file_count": 31,
|
| 98 |
+
"release_payload_total_bytes": 27311072322,
|
| 99 |
+
"repository_id": "RobinY99/MR-IQA-2",
|
| 100 |
+
"schema_version": "mriqa2_hf_export_report_v1",
|
| 101 |
+
"training_asset_count": 1,
|
| 102 |
+
"training_assets": [
|
| 103 |
+
{
|
| 104 |
+
"asset_id": "portable-original-score-cache-v1",
|
| 105 |
+
"bytes": 15003648,
|
| 106 |
+
"path": "training_assets/original_score_cache.sqlite",
|
| 107 |
+
"row_count": 10073,
|
| 108 |
+
"sample_count": 10073,
|
| 109 |
+
"sha256": "7d5410f57f17ff1957e7cbeef951ac01973c0bce97da6f700d61bb222bdd5532"
|
| 110 |
+
}
|
| 111 |
+
]
|
| 112 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248044,
|
| 5 |
+
248046
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "5.12.1",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
judge/README.md
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Judge checkpoint
|
| 2 |
+
|
| 3 |
+
`judge/source-e5` is the frozen step-725 IQA Judge used by the training and
|
| 4 |
+
evaluation pipeline.
|
judge/source-e5/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
judge/source-e5/config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 2560,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 9216,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": 248044,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": true,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": true,
|
| 91 |
+
"transformers_version": "5.12.1",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 24,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1024,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4096,
|
| 103 |
+
"model_type": "qwen3_5_vision",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 2560,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
judge/source-e5/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248044,
|
| 5 |
+
248046
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "5.12.1",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
judge/source-e5/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c75ddabb26f9c00abfe462fc6038079c88576aa6fee406a669f76881e3bf2f1b
|
| 3 |
+
size 4972947968
|
judge/source-e5/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b11a6610858678b3dfed3c06803818ae1d5bfcfe366374f515e08410283a2c9
|
| 3 |
+
size 4105672464
|
judge/source-e5/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,731 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 504320,
|
| 4 |
+
"total_size": 9078531072
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 730 |
+
}
|
| 731 |
+
}
|
judge/source-e5/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
judge/source-e5/processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
judge/source-e5/provenance.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"asset_id": "source-e5-judge-step725",
|
| 3 |
+
"exported_at_utc": "2026-08-10T08:34:19.797359+00:00",
|
| 4 |
+
"exporter_version": "mriqa2_hf_export_v1",
|
| 5 |
+
"files": [
|
| 6 |
+
{
|
| 7 |
+
"name": "model-00001-of-00002.safetensors",
|
| 8 |
+
"sha256": "c75ddabb26f9c00abfe462fc6038079c88576aa6fee406a669f76881e3bf2f1b",
|
| 9 |
+
"size_bytes": 4972947968
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"name": "model-00002-of-00002.safetensors",
|
| 13 |
+
"sha256": "0b11a6610858678b3dfed3c06803818ae1d5bfcfe366374f515e08410283a2c9",
|
| 14 |
+
"size_bytes": 4105672464
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"name": "model.safetensors.index.json",
|
| 18 |
+
"sha256": "044807d4c2f35cc7f9ffbbbe0bd9800256e27f5337069cd69e6c8eba0c98e604",
|
| 19 |
+
"size_bytes": 66232
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"name": "config.json",
|
| 23 |
+
"sha256": "c5635b1910c68e43527ed092d9f964cc0ae0e6b97f91cb0dda9878dba8e5de99",
|
| 24 |
+
"size_bytes": 2929
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"name": "generation_config.json",
|
| 28 |
+
"sha256": "f7c35afc4eda09ee1a9cbe029b030dc9875ab3c201401c48044448e8153acea2",
|
| 29 |
+
"size_bytes": 138
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"name": "preprocessor_config.json",
|
| 33 |
+
"sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
|
| 34 |
+
"size_bytes": 390
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"name": "processor_config.json",
|
| 38 |
+
"sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
|
| 39 |
+
"size_bytes": 1191
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"name": "tokenizer.json",
|
| 43 |
+
"sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
|
| 44 |
+
"size_bytes": 19989325
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"name": "tokenizer_config.json",
|
| 48 |
+
"sha256": "792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b",
|
| 49 |
+
"size_bytes": 1165
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"name": "chat_template.jinja",
|
| 53 |
+
"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
|
| 54 |
+
"size_bytes": 7756
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"hub_subfolder": "judge/source-e5",
|
| 58 |
+
"schema_version": "mriqa2_checkpoint_provenance_v1",
|
| 59 |
+
"selection": {
|
| 60 |
+
"recommended": true,
|
| 61 |
+
"research_status": "required_for_released_judge_protocol",
|
| 62 |
+
"status": "frozen_source_judge"
|
| 63 |
+
},
|
| 64 |
+
"source_identity": {
|
| 65 |
+
"file_count": 10,
|
| 66 |
+
"ignored_source_entries": [
|
| 67 |
+
{
|
| 68 |
+
"kind": "file",
|
| 69 |
+
"name": "provenance.json"
|
| 70 |
+
}
|
| 71 |
+
],
|
| 72 |
+
"selected_export_tree_sha256": "21b232a1a30dc765f3e7cf16c00fd270e4be354615fea0120e32f975e2777e5c",
|
| 73 |
+
"source_checkpoint_tree_sha256_recorded": "e25415173aacf515e97d5d561c6647a7a84f586061f3a9b2ab3fc079fe21be0a",
|
| 74 |
+
"total_bytes": 9098689558
|
| 75 |
+
},
|
| 76 |
+
"source_logical_id": "source-e5-judge-step725",
|
| 77 |
+
"training": {
|
| 78 |
+
"base_model": "Qwen/Qwen3.5-4B",
|
| 79 |
+
"epoch": 5,
|
| 80 |
+
"global_step": 725,
|
| 81 |
+
"mode": "source_e5_judge"
|
| 82 |
+
},
|
| 83 |
+
"validation": {
|
| 84 |
+
"mae": 0.43932,
|
| 85 |
+
"plcc": 0.94797,
|
| 86 |
+
"srcc": 0.934169
|
| 87 |
+
}
|
| 88 |
+
}
|
judge/source-e5/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
judge/source-e5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d75ecd7028d83e74af8bbd0791c55f74062c1d4ac030f149dfc81de7681d382
|
| 3 |
+
size 4972947968
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d492fb65ac0330c50d50d1bd233db966fc71a1236799c1472c55b3c4171cbca9
|
| 3 |
+
size 4105672464
|
model-index.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "MR-IQA-2",
|
| 3 |
+
"metadata": {
|
| 4 |
+
"default_checkpoint": "actor-field-e5-step1455",
|
| 5 |
+
"architecture": "Qwen3.5-4B vision-language Actor",
|
| 6 |
+
"training_method": "GRPO with field-specific reward credit and component KL",
|
| 7 |
+
"global_step": 1455
|
| 8 |
+
},
|
| 9 |
+
"results": [
|
| 10 |
+
{
|
| 11 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 12 |
+
"dataset": {"type": "mriqa2-validation", "name": "MR-IQA-2 validation", "split": "validation"},
|
| 13 |
+
"metrics": [
|
| 14 |
+
{"type": "plcc", "name": "PLCC", "value": 0.9353936795729616},
|
| 15 |
+
{"type": "srcc", "name": "SRCC", "value": 0.919533309066156},
|
| 16 |
+
{"type": "mae", "name": "MAE", "value": 0.3545886555344741}
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 21 |
+
"dataset": {"type": "agiqa-3k", "name": "AGIQA-3K", "split": "test"},
|
| 22 |
+
"metrics": [
|
| 23 |
+
{"type": "plcc", "name": "PLCC", "value": 0.8089118573591103},
|
| 24 |
+
{"type": "srcc", "name": "SRCC", "value": 0.7390947670085277},
|
| 25 |
+
{"type": "mae", "name": "MAE", "value": 0.6014617624138223}
|
| 26 |
+
]
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 30 |
+
"dataset": {"type": "csiq", "name": "CSIQ", "split": "test"},
|
| 31 |
+
"metrics": [
|
| 32 |
+
{"type": "plcc", "name": "PLCC", "value": 0.8243991239798405},
|
| 33 |
+
{"type": "srcc", "name": "SRCC", "value": 0.7850048268015137},
|
| 34 |
+
{"type": "mae", "name": "MAE", "value": 0.5878419449248554}
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 39 |
+
"dataset": {"type": "kadid-10k", "name": "KADID-10K (full)", "split": "test"},
|
| 40 |
+
"metrics": [
|
| 41 |
+
{"type": "plcc", "name": "PLCC", "value": 0.6670232183708812},
|
| 42 |
+
{"type": "srcc", "name": "SRCC", "value": 0.6689211396085699},
|
| 43 |
+
{"type": "mae", "name": "MAE", "value": 0.9759448396378896}
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 48 |
+
"dataset": {"type": "koniq-10k", "name": "KonIQ-10K split", "split": "test"},
|
| 49 |
+
"metrics": [
|
| 50 |
+
{"type": "plcc", "name": "PLCC", "value": 0.9367066509478564},
|
| 51 |
+
{"type": "srcc", "name": "SRCC", "value": 0.9171837930993616},
|
| 52 |
+
{"type": "mae", "name": "MAE", "value": 0.3530841384215857}
|
| 53 |
+
]
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 57 |
+
"dataset": {"type": "live-in-the-wild", "name": "LIVE-Wild", "split": "test"},
|
| 58 |
+
"metrics": [
|
| 59 |
+
{"type": "plcc", "name": "PLCC", "value": 0.8933013124836403},
|
| 60 |
+
{"type": "srcc", "name": "SRCC", "value": 0.8631270242555127},
|
| 61 |
+
{"type": "mae", "name": "MAE", "value": 0.3735409545325385}
|
| 62 |
+
]
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"task": {"type": "image-quality-assessment", "name": "Image Quality Assessment"},
|
| 66 |
+
"dataset": {"type": "spaq", "name": "SPAQ (full)", "split": "test"},
|
| 67 |
+
"metrics": [
|
| 68 |
+
{"type": "plcc", "name": "PLCC", "value": 0.8997301243818722},
|
| 69 |
+
{"type": "srcc", "name": "SRCC", "value": 0.8994066667852589},
|
| 70 |
+
{"type": "mae", "name": "MAE", "value": 0.3664800177687912}
|
| 71 |
+
]
|
| 72 |
+
}
|
| 73 |
+
]
|
| 74 |
+
}
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,731 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 504320,
|
| 4 |
+
"total_size": 9078531072
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 730 |
+
}
|
| 731 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
provenance.template.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "mriqa2_checkpoint_provenance_v1",
|
| 3 |
+
"asset_id": null,
|
| 4 |
+
"source_logical_id": null,
|
| 5 |
+
"hub_subfolder": null,
|
| 6 |
+
"exported_at_utc": null,
|
| 7 |
+
"exporter_version": null,
|
| 8 |
+
"source_identity": {
|
| 9 |
+
"source_checkpoint_tree_sha256_recorded": null,
|
| 10 |
+
"selected_export_tree_sha256": null,
|
| 11 |
+
"file_count": null,
|
| 12 |
+
"total_bytes": null,
|
| 13 |
+
"ignored_source_entries": []
|
| 14 |
+
},
|
| 15 |
+
"training": {
|
| 16 |
+
"mode": null,
|
| 17 |
+
"epoch": null,
|
| 18 |
+
"global_step": null,
|
| 19 |
+
"base_model": "Qwen/Qwen3.5-4B",
|
| 20 |
+
"vision_encoder_frozen": null,
|
| 21 |
+
"aligner_frozen": null
|
| 22 |
+
},
|
| 23 |
+
"selection": {
|
| 24 |
+
"status": null,
|
| 25 |
+
"recommended": null
|
| 26 |
+
},
|
| 27 |
+
"validation": {},
|
| 28 |
+
"files": []
|
| 29 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
training_assets/README.md
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Training asset
|
| 2 |
+
|
| 3 |
+
`original_score_cache.sqlite` contains 10,073 cached source-image ratings from
|
| 4 |
+
`source-e5-judge-step725` for the released training workflow.
|
training_assets/original_score_cache.manifest.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"actor_ids": [
|
| 3 |
+
"source-e5-judge-step725-original-score"
|
| 4 |
+
],
|
| 5 |
+
"bytes": 15003648,
|
| 6 |
+
"dataset_relative_prefix": "koniq-10k/512x384",
|
| 7 |
+
"file": "original_score_cache.sqlite",
|
| 8 |
+
"judge": {
|
| 9 |
+
"model_id": "source-e5-judge-step725",
|
| 10 |
+
"model_tree_sha256": "e25415173aacf515e97d5d561c6647a7a84f586061f3a9b2ab3fc079fe21be0a",
|
| 11 |
+
"model_uri": "hf://RobinY99/MR-IQA-2/judge/source-e5",
|
| 12 |
+
"prompt_hash": "fa78a4ccfd2194a2026ff0b6b722bf22b28f8fa060389c57c4adb1618ac280f6",
|
| 13 |
+
"rating_acceptance_range": [
|
| 14 |
+
0.0,
|
| 15 |
+
5.0
|
| 16 |
+
]
|
| 17 |
+
},
|
| 18 |
+
"omitted_fields": [
|
| 19 |
+
"absolute_paths",
|
| 20 |
+
"ground_truth",
|
| 21 |
+
"image_bytes",
|
| 22 |
+
"raw_completion",
|
| 23 |
+
"reasoning_evidence",
|
| 24 |
+
"reasoning_solution"
|
| 25 |
+
],
|
| 26 |
+
"payload_schema": "vf_original_score_cache_e5_judge_e5prompt_portable_v1",
|
| 27 |
+
"rating": {
|
| 28 |
+
"max": 4.23,
|
| 29 |
+
"mean": 3.1357688871239398,
|
| 30 |
+
"min": 0.83
|
| 31 |
+
},
|
| 32 |
+
"row_count": 10073,
|
| 33 |
+
"sample_count": 10073,
|
| 34 |
+
"schema_version": "mriqa2_portable_original_score_cache_manifest_v1",
|
| 35 |
+
"sha256": "7d5410f57f17ff1957e7cbeef951ac01973c0bce97da6f700d61bb222bdd5532",
|
| 36 |
+
"source": {
|
| 37 |
+
"judge_scores_sha256": "7d16e7aeb2f7693ff78be78fcc02d4c9e456fca2a836956b21ea3a7f689df785",
|
| 38 |
+
"private_cache_sha256": "3ca07c0efe2c208cdb28e4b7769404502a71fc7582bbe0faa37c441aac9de968",
|
| 39 |
+
"source_manifest_sha256": "05ddd93203fbb31a36fed33ae953562d9e79dd993d7a480550a3633a187e4ae6"
|
| 40 |
+
},
|
| 41 |
+
"status": "complete"
|
| 42 |
+
}
|
training_assets/original_score_cache.sqlite
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d5410f57f17ff1957e7cbeef951ac01973c0bce97da6f700d61bb222bdd5532
|
| 3 |
+
size 15003648
|